{"id":"https://openalex.org/W4402917127","doi":"https://doi.org/10.1109/icip51287.2024.10647485","title":"Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation","display_name":"Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402917127","doi":"https://doi.org/10.1109/icip51287.2024.10647485"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103364083","display_name":"Juhyeong Seon","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Juhyeong Seon","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043449123","display_name":"Woobin Im","orcid":"https://orcid.org/0000-0002-9269-4833"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woobin Im","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038468577","display_name":"Sebin Lee","orcid":"https://orcid.org/0000-0002-8927-0319"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sebin Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040184379","display_name":"Jumin Lee","orcid":"https://orcid.org/0000-0002-1008-0118"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jumin Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078173428","display_name":"Sung\u2010Eui Yoon","orcid":"https://orcid.org/0000-0002-7123-1119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung-Eui Yoon","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103364083"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.8752,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86727701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2480","last_page":"2486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.967199981212616,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.967199981212616,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9503999948501587,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9449999928474426,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7582981586456299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7351810336112976},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.645409345626831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5343771576881409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46627169847488403},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43421223759651184},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42580389976501465},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33800438046455383},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2436891794204712},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.16881749033927917}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7582981586456299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351810336112976},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.645409345626831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5343771576881409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46627169847488403},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43421223759651184},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42580389976501465},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33800438046455383},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2436891794204712},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.16881749033927917}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2962865004","https://openalex.org/W3093287838","https://openalex.org/W3118120400","https://openalex.org/W3126721948","https://openalex.org/W3170088426","https://openalex.org/W4221139382","https://openalex.org/W4313123347","https://openalex.org/W4313156423","https://openalex.org/W4383180710","https://openalex.org/W4385481295","https://openalex.org/W4385767885","https://openalex.org/W4386072368","https://openalex.org/W4387969151","https://openalex.org/W4387969495","https://openalex.org/W4390872864","https://openalex.org/W4390874575","https://openalex.org/W4393159433","https://openalex.org/W6729831399","https://openalex.org/W6759579507","https://openalex.org/W6850787431","https://openalex.org/W6851980744","https://openalex.org/W6852501939","https://openalex.org/W6852629184","https://openalex.org/W6852789751","https://openalex.org/W6852820501","https://openalex.org/W6853270349","https://openalex.org/W6853582152","https://openalex.org/W6853805853","https://openalex.org/W6853833822","https://openalex.org/W6854424100","https://openalex.org/W6854713258"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"Audio-visual":[0],"segmentation":[1,58],"(AVS)":[2],"aims":[3],"to":[4,82,125],"segment":[5],"sound":[6],"sources":[7],"in":[8],"the":[9,20,38,51,60,77,83,94,110,122,127,131,145],"video":[10,132],"sequence,":[11],"requiring":[12],"a":[13,47,101,158],"pixel-level":[14],"understanding":[15],"of":[16,30,40,50,66,79,85,112],"audiovisual":[17],"correspondence.":[18],"As":[19],"Segment":[21],"Anything":[22],"Model":[23],"(SAM)":[24],"has":[25],"strongly":[26],"impacted":[27],"extensive":[28],"fields":[29],"dense":[31],"prediction":[32],"problems,":[33],"prior":[34],"works":[35],"have":[36],"investigated":[37],"introduction":[39],"SAM":[41],"into":[42,109],"AVS":[43,149],"with":[44,152],"audio":[45,135],"as":[46],"new":[48],"modality":[49],"prompt.":[52],"Nevertheless,":[53],"constrained":[54],"by":[55,88],"SAM\u2019s":[56,80,113],"single-frame":[57],"scheme,":[59],"temporal":[61],"context":[62],"across":[63,93],"multiple":[64],"frames":[65,133],"audio-visual":[67,86,123],"data":[68],"remains":[69],"insufficiently":[70],"utilized.":[71],"To":[72,96],"this":[73],"end,":[74],"we":[75,99],"study":[76],"extension":[78],"capabilities":[81],"sequence":[84],"scenes":[87],"analyzing":[89],"contextual":[90],"cross-modal":[91],"relationships":[92],"frames.":[95],"achieve":[97],"this,":[98],"propose":[100],"Spatio-Temporal,":[102],"Bidirectional":[103],"Audio-Visual":[104],"Attention":[105],"(ST-BAVA)":[106],"module":[107],"integrated":[108],"middle":[111],"image":[114],"encoder":[115],"and":[116,134],"mask":[117],"decoder.":[118],"It":[119],"adaptively":[120],"updates":[121],"features":[124],"convey":[126],"spatio-temporal":[128],"correspondence":[129],"between":[130],"streams.":[136],"Extensive":[137],"experiments":[138],"demonstrate":[139],"that":[140],"our":[141],"proposed":[142],"model":[143],"outperforms":[144],"state-of-the-art":[146],"methods":[147],"on":[148,157],"benchmarks,":[150],"especially":[151],"an":[153],"8.3%":[154],"mIoU":[155],"gain":[156],"challenging":[159],"multi-sources":[160],"subset.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}